Search Results for author: Yuan Dong

Found 11 papers, 3 papers with code

PanoContext-Former: Panoramic Total Scene Understanding with a Transformer

no code implementations21 May 2023 Yuan Dong, Chuan Fang, Liefeng Bo, Zilong Dong, Ping Tan

Panoramic image enables deeper understanding and more holistic perception of $360^\circ$ surrounding environment, which can naturally encode enriched scene context information compared to standard perspective image.

3D Object Detection object-detection +1

PanoViT: Vision Transformer for Room Layout Estimation from a Single Panoramic Image

no code implementations23 Dec 2022 Weichao Shen, Yuan Dong, Zonghao Chen, Zhengyi Zhao, Yang Gao, Zhu Liu

In this paper, we propose PanoViT, a panorama vision transformer to estimate the room layout from a single panoramic image.

Room Layout Estimation

Caption Feature Space Regularization for Audio Captioning

1 code implementation18 Apr 2022 Yiming Zhang, Hong Yu, Ruoyi Du, Zhanyu Ma, Yuan Dong

To eliminate this negative effect, in this paper, we propose a two-stage framework for audio captioning: (i) in the first stage, via the contrastive learning, we construct a proxy feature space to reduce the distances between captions correlated to the same audio, and (ii) in the second stage, the proxy feature space is utilized as additional supervision to encourage the model to be optimized in the direction that benefits all the correlated captions.

Audio captioning Contrastive Learning

Modeling Clothing as a Separate Layer for an Animatable Human Avatar

no code implementations28 Jun 2021 Donglai Xiang, Fabian Prada, Timur Bagautdinov, Weipeng Xu, Yuan Dong, He Wen, Jessica Hodgins, Chenglei Wu

To address these difficulties, we propose a method to build an animatable clothed body avatar with an explicit representation of the clothing on the upper body from multi-view captured videos.

Inverse Rendering

TLRM: Task-level Relation Module for GNN-based Few-Shot Learning

no code implementations25 Jan 2021 Yurong Guo, Zhanyu Ma, Xiaoxu Li, Yuan Dong

We consider this method of measuring relation of samples only models the sample-to-sample relation, while neglects the specificity of different tasks.

Few-Shot Learning Specificity

Inverse Structural Design of Graphene/Boron Nitride Hybrids by Regressional GAN

1 code implementation21 Aug 2019 Yuan Dong, Dawei Li, Chi Zhang, Chuhan Wu, Hong Wang, Ming Xin, Jianlin Cheng, Jian Lin

A significant novelty of the proposed RGAN is that it combines the supervised and regressional convolutional neural network (CNN) with the traditional unsupervised GAN, thus overcoming the common technical barrier in the traditional GANs, which cannot generate data associated with given continuous quantitative labels.

Computational Physics Materials Science Applied Physics

MSFD:Multi-Scale Receptive Field Face Detector

no code implementations11 Mar 2019 Qiushan Guo, Yuan Dong, Yu Guo, Hongliang Bai

We simultaneously propose an anchor assignment strategy which can cover faces with a wide range of scales to improve the recall rate of small faces and rotated faces.

Multi-hierarchical Independent Correlation Filters for Visual Tracking

1 code implementation26 Nov 2018 Shuai Bai, Zhiqun He, Ting-Bing Xu, Zheng Zhu, Yuan Dong, Hongliang Bai

For visual tracking, most of the traditional correlation filters (CF) based methods suffer from the bottleneck of feature redundancy and lack of motion information.

Motion Estimation Visual Object Tracking +1

Deep Learning Bandgaps of Topologically Doped Graphene

no code implementations28 Sep 2018 Yuan Dong, Chuhan Wu, Chi Zhang, Yingda Liu, Jianlin Cheng, Jian Lin

Moreover, given ubiquitous existence of topologies in materials, this work will stimulate widespread interests in applying deep learning algorithms to topological design of materials crossing atomic, nano-, meso-, and macro- scales.

Materials Science Computational Physics

BodyFusion: Real-Time Capture of Human Motion and Surface Geometry Using a Single Depth Camera

no code implementations ICCV 2017 Tao Yu, Kaiwen Guo, Feng Xu, Yuan Dong, Zhaoqi Su, Jianhui Zhao, Jianguo Li, Qionghai Dai, Yebin Liu

To reduce the ambiguities of the non-rigid deformation parameterization on the surface graph nodes, we take advantage of the internal articulated motion prior for human performance and contribute a skeleton-embedded surface fusion (SSF) method.

Surface Reconstruction

Cannot find the paper you are looking for? You can Submit a new open access paper.